Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import pandas as pd
 import numpy as np
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer
-# summary function - test for single gradio function interfrace
+# summary function - test for single gradio function interface
 def bulk_function(filename):
   # Create class for data preparation
   class SimpleDataset:
@@ -22,15 +22,13 @@ def bulk_function(filename):
   trainer = Trainer(model=model)  
 
   # read file lines
-  with open("/content/YOUR_FILENAME.csv", "r") as f:
+  with open(filename.name, "r") as f:
     lines = f.readlines()
   # expects unnamed:0 or index, col name -> strip both
-  lines_s = [item.split("\n")[0].split(",")[-1] for item in lines][1:]
-  print(lines_s[1:])
- 
+  lines_s = [item.split("\n")[0].split(",")[-1] for item in lines]
 
     # Tokenize texts and create prediction data set
-  tokenized_texts = tokenizer(lines_s[1:],truncation=True,padding=True)
+  tokenized_texts = tokenizer(lines_s,truncation=True,padding=True)
   pred_dataset = SimpleDataset(tokenized_texts)
 
     # Run predictions
@@ -54,7 +52,7 @@ def bulk_function(filename):
   surprise = []
 
   # extract scores (as many entries as exist in pred_texts)
-  for i in range(len(lines_s[1:])):
+  for i in range(len(lines_s)):
     anger.append(temp[i][0])
     disgust.append(temp[i][1])
     fear.append(temp[i][2])
@@ -64,7 +62,7 @@ def bulk_function(filename):
     surprise.append(temp[i][6])
 
   # define df
-  df = pd.DataFrame(list(zip(lines_s[1:],preds,labels,scores,  anger, disgust, fear, joy, neutral, sadness, surprise)), columns=['text','pred','label','score', 'anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'surprise'])
+  df = pd.DataFrame(list(zip(lines_s,preds,labels,scores,  anger, disgust, fear, joy, neutral, sadness, surprise)), columns=['text','pred','label','score', 'anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'surprise'])
 
   # save results to csv
   YOUR_FILENAME = "YOUR_FILENAME_EMOTIONS_gradio.csv"  # name your output file